Automatic detection of left ventricular borders on electron beam CT sequential cardiac images using an adaptive algorithm

• Published in: Computerized medical imaging and graphics 1998-07, Vol.22 (4), p.291-299
• Main Authors: Herment, A., Mousseaux, E., Dumée, P., Decesare, A.
• Format: Article
• Language: English
• Subjects: Algorithms; Biological and medical sciences; Cardiac function; Cardiac morphology; Cardiac Output, Low - diagnostic imaging; Cardiac Output, Low - physiopathology; Cardiomyopathy, Dilated - diagnostic imaging; Cardiomyopathy, Dilated - physiopathology; Cardiomyopathy, Hypertrophic - diagnostic imaging; Cardiomyopathy, Hypertrophic - physiopathology; Cardiovascular system; Contrast Media - administration & dosage; Electron Beam Computerized Tomography; Endocardium - diagnostic imaging; Heart Ventricles - diagnostic imaging; Humans; Image Processing, Computer-Assisted - methods; Investigative techniques, diagnostic techniques (general aspects); Medical sciences; Observer Variation; Pericardium - diagnostic imaging; Radiodiagnosis. Nmr imagery. Nmr spectrometry; Radiographic Image Enhancement; Reproducibility of Results; Segmentation; Tomography, X-Ray Computed; Ventricular Dysfunction, Left - diagnostic imaging; Ventricular Dysfunction, Left - physiopathology; Ventricular Function - physiology
• ISSN: 0895-6111; 1879-0771
• DOI: 10.1016/S0895-6111(98)00034-2

Detection of myocardial borders on sequences of electron beam CT images is carried out using an adaptive segmentation algorithm developed to enhance dynamic analysis of cardiac function. Adaptivity is based on description of the myocardial borders from the mean and standard deviation of the grey level and gradient distributions on each image of the sequence. Comparison of segmentations from five experimentators with automatically determined borders on a set of 416 endocardial and epicardial contours indicated differences between automatic and manual tracing very close to differences due to inter-observer reproducibility.